© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46346
    Prev
    Next
    INDEX
    Explanations

    footnotes and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    engl
    -0.08
    onz
    -0.08
    rieb
    -0.08
    OLUTE
    -0.08
    æĭįæĭį
    -0.07
    jong
    -0.07
    .Tasks
    -0.07
    عÙĪ
    -0.07
     Knights
    -0.07
    ipse
    -0.07
    POSITIVE LOGITS
     footnote
    0.09
     corrections
    0.08
     Corrections
    0.08
     versehen
    0.08
    foot
    0.08
     alt
    0.07
     note
    0.07
     foot
    0.07
     numbering
    0.07
    notes
    0.07
    Activations Density 0.055%

    No Known Activations